Codex: model API costs and setup

The current Codex provider reference supports the Responses wire protocol. Meldport's public contract currently documents Chat Completions instead.

Direct connection unavailable for current documented protocol. Documentation checked 2026-11-02.

Protocol and setup checks

Steps below are per vendor documentation. Read the official Codex documentation.

1. Check model_providers.<id>.wire_api in the official reference for your installed client.
2. Verify /v1/responses support on the intended endpoint before configuring a custom provider.
3. Current documentation lists responses as the supported wire_api value. Do not copy an old wire_api = chat example for Meldport. Use a Responses-compatible endpoint or a separately tested adapter.

Calculate cost before comparing savings

For GLM 5.3 Flash, verified on 2026-11-06, the listed uncached rates are $0.045 input and $0.15 output per million tokens. An illustrative 100,000 input plus 10,000 output tokens costs $0.006000, before minimum charges, caching, retries, and any other fees. This does not establish that the model works with Codex.

Repeat the calculation using the same token counts and model at another provider. Savings exist only when that comparable total is higher. A lower rate does not establish equal quality, latency, or fewer retries.

Compare current token prices, review Meldport's API contract, and plan a task budget.

Confirm protocol compatibility before buying credit for this client. Compare the other agent connection options.